Commit
•
3db5359
1
Parent(s):
a428bf9
End of training
Browse files- README.md +34 -179
- adapter_config.json +43 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +4 -0
- runs/Jul07_12-33-55_91d12bb143a1/events.out.tfevents.1720355919.91d12bb143a1.14621.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +61 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,201 +1,56 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
tags:
|
4 |
- trl
|
5 |
- sft
|
|
|
|
|
|
|
|
|
6 |
---
|
7 |
|
8 |
-
|
|
|
9 |
|
10 |
-
|
11 |
|
|
|
12 |
|
|
|
13 |
|
14 |
-
|
15 |
|
16 |
-
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
21 |
|
22 |
-
|
23 |
-
- **Funded by [optional]:** [More Information Needed]
|
24 |
-
- **Shared by [optional]:** [More Information Needed]
|
25 |
-
- **Model type:** [More Information Needed]
|
26 |
-
- **Language(s) (NLP):** [More Information Needed]
|
27 |
-
- **License:** [More Information Needed]
|
28 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
29 |
|
30 |
-
|
31 |
|
32 |
-
|
33 |
|
34 |
-
|
35 |
-
-
|
36 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
-
|
39 |
|
40 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
41 |
|
42 |
-
### Direct Use
|
43 |
|
44 |
-
|
45 |
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
[More Information Needed]
|
53 |
-
|
54 |
-
### Out-of-Scope Use
|
55 |
-
|
56 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
57 |
-
|
58 |
-
[More Information Needed]
|
59 |
-
|
60 |
-
## Bias, Risks, and Limitations
|
61 |
-
|
62 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
63 |
-
|
64 |
-
[More Information Needed]
|
65 |
-
|
66 |
-
### Recommendations
|
67 |
-
|
68 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
69 |
-
|
70 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
71 |
-
|
72 |
-
## How to Get Started with the Model
|
73 |
-
|
74 |
-
Use the code below to get started with the model.
|
75 |
-
|
76 |
-
[More Information Needed]
|
77 |
-
|
78 |
-
## Training Details
|
79 |
-
|
80 |
-
### Training Data
|
81 |
-
|
82 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
83 |
-
|
84 |
-
[More Information Needed]
|
85 |
-
|
86 |
-
### Training Procedure
|
87 |
-
|
88 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
89 |
-
|
90 |
-
#### Preprocessing [optional]
|
91 |
-
|
92 |
-
[More Information Needed]
|
93 |
-
|
94 |
-
|
95 |
-
#### Training Hyperparameters
|
96 |
-
|
97 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
98 |
-
|
99 |
-
#### Speeds, Sizes, Times [optional]
|
100 |
-
|
101 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
102 |
-
|
103 |
-
[More Information Needed]
|
104 |
-
|
105 |
-
## Evaluation
|
106 |
-
|
107 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
108 |
-
|
109 |
-
### Testing Data, Factors & Metrics
|
110 |
-
|
111 |
-
#### Testing Data
|
112 |
-
|
113 |
-
<!-- This should link to a Dataset Card if possible. -->
|
114 |
-
|
115 |
-
[More Information Needed]
|
116 |
-
|
117 |
-
#### Factors
|
118 |
-
|
119 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
120 |
-
|
121 |
-
[More Information Needed]
|
122 |
-
|
123 |
-
#### Metrics
|
124 |
-
|
125 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
126 |
-
|
127 |
-
[More Information Needed]
|
128 |
-
|
129 |
-
### Results
|
130 |
-
|
131 |
-
[More Information Needed]
|
132 |
-
|
133 |
-
#### Summary
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
## Model Examination [optional]
|
138 |
-
|
139 |
-
<!-- Relevant interpretability work for the model goes here -->
|
140 |
-
|
141 |
-
[More Information Needed]
|
142 |
-
|
143 |
-
## Environmental Impact
|
144 |
-
|
145 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
146 |
-
|
147 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
148 |
-
|
149 |
-
- **Hardware Type:** [More Information Needed]
|
150 |
-
- **Hours used:** [More Information Needed]
|
151 |
-
- **Cloud Provider:** [More Information Needed]
|
152 |
-
- **Compute Region:** [More Information Needed]
|
153 |
-
- **Carbon Emitted:** [More Information Needed]
|
154 |
-
|
155 |
-
## Technical Specifications [optional]
|
156 |
-
|
157 |
-
### Model Architecture and Objective
|
158 |
-
|
159 |
-
[More Information Needed]
|
160 |
-
|
161 |
-
### Compute Infrastructure
|
162 |
-
|
163 |
-
[More Information Needed]
|
164 |
-
|
165 |
-
#### Hardware
|
166 |
-
|
167 |
-
[More Information Needed]
|
168 |
-
|
169 |
-
#### Software
|
170 |
-
|
171 |
-
[More Information Needed]
|
172 |
-
|
173 |
-
## Citation [optional]
|
174 |
-
|
175 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
176 |
-
|
177 |
-
**BibTeX:**
|
178 |
-
|
179 |
-
[More Information Needed]
|
180 |
-
|
181 |
-
**APA:**
|
182 |
-
|
183 |
-
[More Information Needed]
|
184 |
-
|
185 |
-
## Glossary [optional]
|
186 |
-
|
187 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
188 |
-
|
189 |
-
[More Information Needed]
|
190 |
-
|
191 |
-
## More Information [optional]
|
192 |
-
|
193 |
-
[More Information Needed]
|
194 |
-
|
195 |
-
## Model Card Authors [optional]
|
196 |
-
|
197 |
-
[More Information Needed]
|
198 |
-
|
199 |
-
## Model Card Contact
|
200 |
-
|
201 |
-
[More Information Needed]
|
|
|
1 |
---
|
2 |
+
base_model: llava-hf/llava-1.5-7b-hf
|
3 |
+
library_name: peft
|
4 |
tags:
|
5 |
- trl
|
6 |
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: llva-1.5-7b-scicap
|
10 |
+
results: []
|
11 |
---
|
12 |
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
+
# llva-1.5-7b-scicap
|
17 |
|
18 |
+
This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on an unknown dataset.
|
19 |
|
20 |
+
## Model description
|
21 |
|
22 |
+
More information needed
|
23 |
|
24 |
+
## Intended uses & limitations
|
25 |
|
26 |
+
More information needed
|
27 |
|
28 |
+
## Training and evaluation data
|
29 |
|
30 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
|
32 |
+
## Training procedure
|
33 |
|
34 |
+
### Training hyperparameters
|
35 |
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1.4e-05
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 1
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
|
46 |
+
### Training results
|
47 |
|
|
|
48 |
|
|
|
49 |
|
50 |
+
### Framework versions
|
51 |
|
52 |
+
- PEFT 0.11.1
|
53 |
+
- Transformers 4.42.3
|
54 |
+
- Pytorch 2.3.0+cu121
|
55 |
+
- Datasets 2.20.0
|
56 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.llava.modeling_llava"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_dropout": 0.0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 64,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"up_proj",
|
27 |
+
"k_proj",
|
28 |
+
"v_proj",
|
29 |
+
"linear_2",
|
30 |
+
"o_proj",
|
31 |
+
"linear_1",
|
32 |
+
"out_proj",
|
33 |
+
"fc2",
|
34 |
+
"gate_proj",
|
35 |
+
"lm_head",
|
36 |
+
"q_proj",
|
37 |
+
"down_proj",
|
38 |
+
"fc1"
|
39 |
+
],
|
40 |
+
"task_type": null,
|
41 |
+
"use_dora": false,
|
42 |
+
"use_rslora": false
|
43 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19dc14c53bafe6afa9c78a930a383b628cace71e3e0803bf68c9359b0a544605
|
3 |
+
size 1290994752
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image>": 32000,
|
3 |
+
"<pad>": 32001
|
4 |
+
}
|
runs/Jul07_12-33-55_91d12bb143a1/events.out.tfevents.1720355919.91d12bb143a1.14621.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96de2fa228276c52b411f80682e4d95f202c4448683e1c54a74a67980c468e5e
|
3 |
+
size 10475
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<image>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<pad>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"chat_template": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. {% for message in messages %}{% if message['role'] == 'user' %} USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %} {% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}",
|
49 |
+
"clean_up_tokenization_spaces": false,
|
50 |
+
"eos_token": "</s>",
|
51 |
+
"legacy": false,
|
52 |
+
"model_max_length": 1000000000000000019884624838656,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"padding_side": "left",
|
55 |
+
"processor_class": "LlavaProcessor",
|
56 |
+
"sp_model_kwargs": {},
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"trust_remote_code": false,
|
59 |
+
"unk_token": "<unk>",
|
60 |
+
"use_default_system_prompt": false
|
61 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7922fefb0f15a9505ad74fb2b0c736514ee911fe6c680d3eb0e287f8f1526692
|
3 |
+
size 5432
|